NUWA RESEARCH RECORD
What Victims Take Away: Attack Reuse and Defense Revision after Prompt-Injection Attacks
Original publication ↗ · BibTeX · RISSuccessful received attacks were reused more often than matched unreceived attacks; breached players also changed defenses. The authors propose testing disclosure designs that preserve diagnosis while limiting reusable text.
Research question
Does exposing received prompt-injection text help defense while also enabling reuse?
Design & assumptions
The study compares received game attacks with matched circulating attacks and follows defense revisions and subsequent reuse.
Findings
Successful received attacks were reused more often than matched unreceived attacks; breached players also changed defenses. The authors propose testing disclosure designs that preserve diagnosis while limiting reusable text.
Limits & counterevidence
This observational game study cannot by itself establish effects in production security interfaces. Matching reduces specified confounds but does not make exposure randomized.
Source evidence
No structured numerical extraction is available in this reading package.
Reading scope & review
Selected original HTML sections and table context; not a complete paper/appendix audit or independent reproduction.
Model-assisted reading; independent evidence review pending.
Check the original source ↗